Two or more learning images generated for a first subject or a second subject and one or more correct answer images generated for the second subject or a third subject are received. In a case where pixel values of corresponding pixels of the two or more learning images are synthesized by using a synthesis parameter value, the parameter value at which the synthesized pixel values are close to a pixel value of a corresponding pixel of the correct answer image is obtained. An image generated for the first subject and having the same type as the two or more learning images is received as an examination target image. A synthesized image desired by a user is generated by synthesizing pixel values of corresponding pixels of the two or more examination target images by using the synthesis parameter value.
Legal claims defining the scope of protection, as filed with the USPTO.
Claim text for this patent isn't available yet.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
March 22, 2019
August 30, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.